AI Transformation Engineer
Yext · New York, NY
About this role
**Yext — AI Transformation Engineer** Yext (NYSE: YEXT) is the enterprise agentic marketing platform. The AI Transformation Office partners with departments across Yext to improve business outcomes through **30–60 day transformation sprints**. As an **AI Transformation Engineer**, you build the production systems that make these sprints real—covering **retrieval, answer drafting, routing, and evaluation on live data**, plus the **APIs, automations, and pipelines** around them. Each sprint ends with a handoff to the team that owns the outcome. > This is **not** a product-roadmap engineering role. You embed with department teams, learn how work actually gets done, and build using whatever fits—often a workflow platform such as **n8n** (code only where the platform runs out). You care as much about whether someone else can run your work as whether it runs in production. --- ## What You’ll Do ### Production LLM systems (40%) - Build and run production LLM workflows in **n8n** and similar platforms (e.g., retrieval over ticket/documentation data, answer drafting and routing). - Build **APIs, integrations, and data pipelines** connecting CRM, support, and operational systems. - Build and calibrate **confidence scoring** so teams know when to trust an answer; design review steps and approval gates. - Protect data: scope workflow access, handle **PII/sensitive fields**, and keep **access logs**. - Ship solutions that are **monitored, error-handled, and version-controlled**. ### Evals and quality (15%) - Define evals before each build: test sets, groundedness/accuracy checks, and thresholds for shipping vs. review. - Report quality results to partner teams in plain terms. - Track LLM spend/usage by team; manage API keys and report run rate. ### Knowledge transfer and enablement (20%) - Pair-build with embedded team members so they learn by doing. - Write scalable documentation: runbooks, admin guides, architecture diagrams, decision logs. - Train department champions at the right altitude (enough to maintain/extend, not overwhelm). - Build with handoff in mind from day one—owning teams should be able to run systems day-to-day within ~30 days. ### System design and architecture (15%) - Design integration patterns connecting CRM, support, and operational systems. - Architect data flows enabling automation and AI-powered decisions. - Evaluate new models/tools and recommend build-vs-buy based on real maintenance capacity. ### Opportunity identification (10%) - Spot automation/integration opportunities others miss by understanding how work actually gets done. - Translate technical possibilities into language stakeholders can evaluate. - Estimate effort honestly and scope tightly; cut work that doesn’t change outcomes. --- ## What You Have - **5–8 years** in software engineering, integration development, or automation engineering. - Production experience with workflow platforms such as **n8n, Zapier, or Tray.io**. - Experience designing reliable autonomous agents (tool calling, orchestration, guardrails, human escalation) with eval feedback loops. - **Python or TypeScript** for what platforms can’t do; strong API design and operational discipline (monitoring, error handling, version control, deployment). - Hands-on production use of **LLM APIs** (Anthropic, OpenAI, or Google), including prompt design and structured outputs. - Retrieval experience (e.g., **Qdrant** or **pgvector**, chunking, grounding). - Experience measuring LLM output qua
Listing freshness
CronJobs last confirmed this listing 2h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.